© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20551
    Prev
    Next
    INDEX
    Explanations

    references to competitive events and contests

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious awards or championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    learn
    -0.75
    rete
    -0.73
    onse
    -0.73
    isi
    -0.70
    arry
    -0.69
    chan
    -0.68
    onday
    -0.67
    cohol
    -0.67
    lins
    -0.65
    ombies
    -0.65
    POSITIVE LOGITS
     coveted
    1.26
     mantle
    1.26
     throne
    1.14
     presidency
    1.11
     title
    1.09
     highest
    1.05
     elusive
    0.97
     nomination
    0.97
     lion
    0.97
     hearts
    0.96
    Activations Density 0.147%

    No Known Activations